Fuck AI

4728 readers

466 users here now

"We did it, Patrick! We made a technological breakthrough!"

A place for all those who loathe AI to discuss things, post articles, and ridicule the AI hype. Proud supporter of working people. And proud booer of SXSW 2024.

AI, in this case, refers to LLMs, GPT technology, and anything listed as "AI" meant to increase market valuations.

founded 2 years ago

MODERATORS

VerbFlow@lemmy.world

MrMcGasion@lemmy.world

TootSweet@lemmy.world

BigMikeInAustin@lemmy.world

cynar@lemmy.world

drmeanfeel@lemmy.world

pavnilschanda@lemmy.world

CriticalMedicine@lemmy.world

WonderfulWanderer@lemmy.world

Communist@lemmy.ml

eatCasserole@lemmy.world

SpaceNoodle@lemmy.world

NutWrench@lemmy.world

Soup@lemmy.cafe

iAvicenna@lemmy.world

Tinks@lemmy.world

wizblizz@lemmy.world

corus_kt@lemmy.world

TrickDacy@lemmy.world

andrew_bidlaw@sh.itjust.works

MeDuViNoX@sh.itjust.works

33550336@lemmy.world

Nougat@fedia.io

Lost_My_Mind@lemmy.world

Sterile_Technique@lemmy.world

Quill7513@slrpnk.net

glowing_hans@sopuli.xyz

e8d79@discuss.tchncs.de

ThefuzzyFurryComrade@pawb.social

273

Poets are now cybersecurity threats: Researchers used 'adversarial poetry' to trick AI into ignoring its safety guard rails and it worked 62% of the time (www.pcgamer.com)

submitted 1 week ago* (last edited 1 week ago) by TootSweet@lemmy.world to c/fuck_ai@lemmy.world

23 comments fedilink hide all child comments

Edit: After I posted this, I found out there are serious questions about how true any of this is. See here for more info. But also, self-serving propaganda is pretty strongly on-brand for anything in the "aRtIfIcIaL iNtElLiGeNce"(tm) space.

you are viewing a single comment's thread
view the rest of the comments

[–] RichardDegenne@lemmy.zip 2 points 1 week ago (1 children)

As much as I like to dunk on AI, the methodology of this paper is piss-poor.

[–] Meron35@lemmy.world 3 points 1 week ago

Perhaps, but it is documenting an open secret in the LLM space. System prompts as security is basically the best we have, and it's jank af. People literally have competitions with cracking the latest models, often succeeding within hours of release.

You can get a feel for yourself as well:

Gandalf | Lakera – Test your AI hacking skills - https://gandalf.lakera.ai/